© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1025-7B
    5. 16-RES-MATRYOSHKA-65K
    7. 3247
    Prev
    Next
    INDEX
    Explanations

    ending punctuation followed by conjunctions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    decoderesearch/olmo-3-saes/olmo-3-1025-7b
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    vang
    -0.09
    (&(
    -0.08
    gis
    -0.08
     trading
    -0.08
    hos
    -0.08
     meat
    -0.07
     Marty
    -0.07
    IRT
    -0.07
    ylie
    -0.07
     Nec
    -0.07
    POSITIVE LOGITS
    Anyway
    0.13
     Anyway
    0.12
     anyway
    0.10
    itary
    0.10
    cid
    0.09
    olib
    0.09
    aro
    0.09
    IL
    0.09
    bib
    0.09
    indle
    0.09
    Activations Density 0.513%

    No Known Activations